Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ущ
    -0.07
    $MESS
    -0.07
     طور
    -0.07
    .BAD
    -0.06
    ngoing
    -0.06
    ํ
    -0.06
     Lanka
    -0.06
     zaw
    -0.06
    ankan
    -0.06
    :param
    -0.06
    POSITIVE LOGITS
    /write
    0.07
    енню
    0.07
     Paige
    0.06
     Meter
    0.06
     Solution
    0.06
    _under
    0.06
     stroll
    0.06
    +/
    0.06
    BAR
    0.06
     screenplay
    0.06
    Act Density 0.001%

    No Known Activations